© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8440
    Prev
    Next
    INDEX
    Explanations

    words associated with linear direction ('straight', 'edge', 'forward') or intensive review ('examination', 'specifically')

    oai_token-act-pair · gemini-2.0-flash

    edges, sports, examinations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     мәкал
    -0.63
     khai
    -0.55
    ']>;
    -0.54
    pirable
    -0.54
     suyo
    -0.53
    aniline
    -0.53
    ionine
    -0.53
     giudi
    -0.52
    ecutive
    -0.52
    TAA
    -0.50
    POSITIVE LOGITS
     doInBackground
    0.66
    Datuak
    0.58
     विश्वसनीयता
    0.57
    onAttach
    0.57
    onViewCreated
    0.52
    VideoCapture
    0.52
    ppelin
    0.52
    mtrl
    0.50
    adaptiveStyles
    0.49
    pyx
    0.48
    Activations Density 0.868%

    No Known Activations